Application of Neural Network in Analyzing Torque Coefficient of Hot-Dip Galvanized Fasteners

Hong Yun Yu; Rui Li; Miao Qian; Guo Yong Li; Min Bo Yu; Zhi Hua Zhu; Zhou Xuan Li

doi:10.4028/www.scientific.net/AMR.1065-1069.1374

Paper Titles

The Numerical Simulation for Steel Plate Reinforced Concrete Coupling Beams Based on Abaqus
p.1354

Practical Calculation Method for the Bearing Capacity at High Temperature of Concrete Filled Steel Tubular Columns Subjected to Fire
p.1358

Research on the Synchronous Lifting Process Control of Large-Span Pre-Stressed Double-Layer Suspended Cable Roof
p.1363

The Mechanical Properties of Barite Concrete Subjected to Impact Loading
p.1369

Application of Neural Network in Analyzing Torque Coefficient of Hot-Dip Galvanized Fasteners
p.1374

The Marine Environment Impacts on the Supporting Structure of the Offshore Wind Turbines and Discussions on the Protective Measures
p.1381

A Structural Damage Warning Process Based on Frequency Abnormal Development
p.1390

A Simple Design Procedure of Seismic Reinforcement Structure with Mild Steel Dampers
p.1397

Analysis for Collapse Process of Multi-Layer RC Frame Structures under Earthquakes
p.1402

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 1065-1069Application of Neural Network in Analyzing Torque...

Application of Neural Network in Analyzing Torque Coefficient of Hot-Dip Galvanized Fasteners

Abstract:

Hot-dip galvanized fasteners are key connecting components on power transmission towers and structures. In order to improve the installation code of galvanized fasteners, this paper establishes a three-layer (BP) neural network by using the friction coefficients between threads, nut bearing surface friction coefficients and the associated torque coefficients. In addition, the neural network is trained to predict the torque coefficients of fasteners. It can be seen from the research results that the torque coefficients fall within [0.355, 0.709]. Subsequently, the prediction capability of neural network is verified through tests and statistics upon real galvanized fasteners, proving that BP neural network is an effective model.

You might also be interested in these eBooks

Civil, Structural and Environmental Engineering III

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 1065-1069)

Pages:

1374-1380

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1065-1069.1374

Citation:

Cite this paper

Online since:

December 2014

Authors:

Hong Yun Yu, Rui Li, Miao Qian*, Guo Yong Li, Min Bo Yu, Zhi Hua Zhu, Zhou Xuan Li

Keywords:

Application, Fasteners, Hot-Dip Galvanizing, Neural Network, Prediction, Torque Coefficient

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] GB/T 5267. 3-2008, Fasteners – Hot-dip Galvanized Coatings [S].

Google Scholar

[2] Miao Lixian, Li Bin, Yang Tongfa, and etc. Optimization of Galvanizing Process for Steel Parts of Power Towers, Electroplating & Finishing [J]. 2014, 33(12): 514-516.

Google Scholar

[3] Sun Weiwei, Liu Qiongsun. Combined Optimization of BP Neural Networks, Computer Engineering and Applications [J], 2009, 45.

Google Scholar

[12] 50-51.

Google Scholar

[4] Wen Xin. MATLAB Neural Network Simulation and Application [M]. Beijing: Science Press, (2003).

Google Scholar

[5] Sun Weiwei. Study on Improvement and Application of BP Neural Network Algorithms [D]. Chongqing: Chongqing University, (2009).

Google Scholar

[6] Zhiguo Zhang. Learning Algorithm of Wavelet Network Based on Sampling Theory [J]. Neurocomputing, 2007, 71: 244-269.

DOI: 10.1016/j.neucom.2007.01.001

Google Scholar

[7] GB/T 16823. 2-1997, General Rules of Tightening for Threaded Fasteners [S].

Google Scholar

[8] JJF 1134-2005, Calibration Specification for Working Force Measuring Machines for Special Purposes [S].

Google Scholar

[9] GB/T 16823. 3-1997, Method of Tightening Test for Threaded Fasteners [S].

Google Scholar